<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
small-mlm-glue-qqp-from-scratch-custom-tokenizer
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.9723
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.1744 | 0.4 | 500 | 6.6327 |
| 6.2017 | 0.8 | 1000 | 6.4708 |
| 5.9807 | 1.2 | 1500 | 6.3544 |
| 5.8057 | 1.6 | 2000 | 6.1953 |
| 5.7186 | 2.0 | 2500 | 6.1794 |
| 5.5759 | 2.4 | 3000 | 6.0617 |
| 5.5572 | 2.8 | 3500 | 6.1286 |
| 5.5134 | 3.2 | 4000 | 6.0364 |
| 5.3844 | 3.6 | 4500 | 6.0568 |
| 5.4336 | 4.0 | 5000 | 5.9723 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
